{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3QF4EDTRWX67FBM2UOS7DSSVTS","short_pith_number":"pith:3QF4EDTR","schema_version":"1.0","canonical_sha256":"dc0bc20e71b5fdf2859aa3a5f1ca559cb10b14bbd9fe068b68b01142d455c388","source":{"kind":"arxiv","id":"2408.13119","version":2},"attestation_state":"computed","paper":{"title":"Coarse-to-fine Alignment Makes Better Speech-image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Lifeng Zhou, Yuke Li","submitted_at":"2024-08-15T02:21:49Z","abstract_excerpt":"In this paper, we propose a novel framework for speech-image retrieval. We utilize speech-image contrastive (SIC) learning tasks to align speech and image representations at a coarse level and speech-image matching (SIM) learning tasks to further refine the fine-grained cross-modal alignment. SIC and SIM learning tasks are jointly trained in a unified manner. To optimize the learning process, we utilize an embedding queue that facilitates efficient sampling of high-quality and diverse negative representations during SIC learning. Additionally, it enhances the learning of SIM tasks by effective"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2408.13119","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-15T02:21:49Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"37fb1f8922cdcc7dd11e733a49e369a136481e1b7fc85e0a7d957ca999211986","abstract_canon_sha256":"33a07db4af2aab5bd458ade40552a4bd607bd371689d6fea6e29c5a536855d4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:38.642165Z","signature_b64":"uBnX7MxpQCWKrtttIcBz27Gval6e5/zkURsj/MGF1bL8YA2i/LRpJx0tMjQviIRiwLk1Xa1w0lCt4puAhsoSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc0bc20e71b5fdf2859aa3a5f1ca559cb10b14bbd9fe068b68b01142d455c388","last_reissued_at":"2026-07-05T09:05:38.641686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:38.641686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coarse-to-fine Alignment Makes Better Speech-image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Lifeng Zhou, Yuke Li","submitted_at":"2024-08-15T02:21:49Z","abstract_excerpt":"In this paper, we propose a novel framework for speech-image retrieval. We utilize speech-image contrastive (SIC) learning tasks to align speech and image representations at a coarse level and speech-image matching (SIM) learning tasks to further refine the fine-grained cross-modal alignment. SIC and SIM learning tasks are jointly trained in a unified manner. To optimize the learning process, we utilize an embedding queue that facilitates efficient sampling of high-quality and diverse negative representations during SIC learning. Additionally, it enhances the learning of SIM tasks by effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13119","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.13119/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.13119","created_at":"2026-07-05T09:05:38.641743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13119v2","created_at":"2026-07-05T09:05:38.641743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13119","created_at":"2026-07-05T09:05:38.641743+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QF4EDTRWX67","created_at":"2026-07-05T09:05:38.641743+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QF4EDTRWX67FBM2","created_at":"2026-07-05T09:05:38.641743+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QF4EDTR","created_at":"2026-07-05T09:05:38.641743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19684","citing_title":"Exploring Multi-Modal Large Language Models and Two-Stage Fine-Tuning for Fashion Image Retrieval","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QF4EDTRWX67FBM2UOS7DSSVTS","json":"https://pith.science/pith/3QF4EDTRWX67FBM2UOS7DSSVTS.json","graph_json":"https://pith.science/api/pith-number/3QF4EDTRWX67FBM2UOS7DSSVTS/graph.json","events_json":"https://pith.science/api/pith-number/3QF4EDTRWX67FBM2UOS7DSSVTS/events.json","paper":"https://pith.science/paper/3QF4EDTR"},"agent_actions":{"view_html":"https://pith.science/pith/3QF4EDTRWX67FBM2UOS7DSSVTS","download_json":"https://pith.science/pith/3QF4EDTRWX67FBM2UOS7DSSVTS.json","view_paper":"https://pith.science/paper/3QF4EDTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13119&json=true","fetch_graph":"https://pith.science/api/pith-number/3QF4EDTRWX67FBM2UOS7DSSVTS/graph.json","fetch_events":"https://pith.science/api/pith-number/3QF4EDTRWX67FBM2UOS7DSSVTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QF4EDTRWX67FBM2UOS7DSSVTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QF4EDTRWX67FBM2UOS7DSSVTS/action/storage_attestation","attest_author":"https://pith.science/pith/3QF4EDTRWX67FBM2UOS7DSSVTS/action/author_attestation","sign_citation":"https://pith.science/pith/3QF4EDTRWX67FBM2UOS7DSSVTS/action/citation_signature","submit_replication":"https://pith.science/pith/3QF4EDTRWX67FBM2UOS7DSSVTS/action/replication_record"}},"created_at":"2026-07-05T09:05:38.641743+00:00","updated_at":"2026-07-05T09:05:38.641743+00:00"}